© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20579
    Prev
    Next
    INDEX
    Explanations

    special characters followed by numbers or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åħ«ä¹Ŀ
    -0.06
    ugo
    -0.05
    åħ¨
    -0.05
    uden
    -0.05
    åħĥ
    -0.05
    illo
    -0.05
     tabl
    -0.05
    ipot
    -0.05
    que
    -0.05
    czy
    -0.05
    POSITIVE LOGITS
    éal
    0.06
    管çIJĨæ³ķ
    0.06
    ament
    0.06
    agt
    0.06
    alts
    0.06
    annel
    0.06
    jah
    0.06
    edList
    0.06
    gai
    0.06
    uyente
    0.06
    Activations Density 0.027%

    No Known Activations